Intelligent electric energy meter fault prediction method and device

Abstract

The application provides a kind of smart electric energy meter fault prediction method and device, belong to smart electric energy meter field.This method includes: obtaining the monitoring value of at least one target influencing factor of smart electric energy meter;Judge whether the monitoring value of each target influencing factor is over standard, and record the over standard duration corresponding to each target influencing factor whose monitoring value is over standard;According to the monitoring value and over standard duration of each target influencing factor that is over standard, calculate the cumulative degradation value corresponding to multiple key components in smart electric energy meter;Judge whether the cumulative degradation value corresponding to each key component reaches the preset threshold value corresponding to each key component, if there is key component whose degradation value reaches the corresponding preset threshold value, it is determined as target key component, and target key component is predicted to occur fault.The application can solve the problem that the accuracy of smart electric energy meter fault prediction is not high.

Description

Technical Field

[0001] This invention relates to the field of smart energy meter technology, and in particular to a method and device for predicting faults in smart energy meters. Background Technology

[0002] With the State Grid Corporation of China vigorously promoting the construction of smart grids, smart meters, as an important component of smart electricity consumption, have also experienced rapid development and application. To meet the needs of advanced metering systems, the high reliability of smart meters is crucial.

[0003] The reliability of smart meters is affected by various factors. Current technologies often evaluate the reliability of smart meters based on their overall lifespan. For example, patent application CN201910436990.6 proposes a method for monitoring the lifespan of a smart meter by analyzing temperature and humidity factors to calculate the remaining lifespan and thus predict faults. However, smart meters contain multiple components, and the degradation of any one of these components can lead to meter failure. Therefore, the accuracy of existing methods for fault prediction in smart meters is not high. Summary of the Invention

[0004] This invention provides a method and apparatus for predicting faults in smart energy meters, in order to solve the problem of low accuracy in fault prediction of smart energy meters in the prior art.

[0005] In a first aspect, embodiments of the present invention provide a method for predicting faults in smart energy meters, comprising:

[0006] Acquire monitoring values ​​of at least one target influencing factor of the smart energy meter;

[0007] Determine whether the monitoring values ​​of each target influencing factor exceed the standard, and record the duration of the exceedance corresponding to each target influencing factor whose monitoring value exceeds the standard;

[0008] Based on the monitoring values ​​and duration of each influencing factor that exceeds the standard, calculate the cumulative degradation value corresponding to multiple key components in the smart energy meter;

[0009] Determine whether the cumulative degradation value of each key component has reached the preset threshold for each key component. If there is a key component whose degradation value has reached the preset threshold, then identify it as the target key component and predict that the target key component will fail.

[0010] In conjunction with the first aspect, in one possible implementation of the first aspect, based on the monitoring values ​​and duration of the exceeding of various target influencing factors, the cumulative degradation values ​​corresponding to multiple key components in the smart energy meter are calculated, including:

[0011] For each key component, based on the monitoring values ​​of each target influencing factor that exceeds the standard, the corresponding degradation factor for each target influencing factor that exceeds the standard is determined;

[0012] The degradation value of the key component in this instance is obtained by summing the products of the degradation factor corresponding to each of the influencing factors that exceed the standard and the duration of the exceedance.

[0013] Based on the current degradation value, determine the cumulative degradation value of the critical component.

[0014] In conjunction with the first aspect, in one possible implementation of the first aspect, each key component is pre-programmed with a relationship curve between various target influencing factors and degradation factors;

[0015] For each key component, based on the monitored values ​​of each influencing factor that exceeds the standard, the corresponding degradation factor for each influencing factor that exceeds the standard is determined, including:

[0016] For each key component, based on the monitoring values ​​and relationship curves of each target influencing factor that exceeds the standard, the degradation factor corresponding to each target influencing factor that exceeds the standard is determined.

[0017] In conjunction with the first aspect, in one possible implementation of the first aspect, the relationship curve between the target influencing factor and the degradation factor is determined in the following way:

[0018] For each critical component, the time it takes for the critical component to degrade to failure under multiple different set values ​​of any target influencing factor is obtained, and the degradation factor corresponding to multiple different set values ​​is determined based on the time; wherein, the degradation factor is inversely proportional to time;

[0019] By fitting the degradation factor corresponding to multiple different set values ​​of the target influencing factor, the relationship curve between the target influencing factor and the degradation factor corresponding to the key component is obtained.

[0020] In conjunction with the first aspect, in one possible implementation of the first aspect, multiple key components include a first type of key component, which is a key component that affects the metering accuracy of the smart energy meter.

[0021] The method also includes:

[0022] If the cumulative degradation value corresponding to each type of key component does not reach the preset threshold corresponding to each type of key component, then the metering accuracy offset value of the smart energy meter is calculated based on the cumulative degradation value corresponding to each type of key component.

[0023] Based on the metering accuracy offset value, predict whether the smart energy meter is faulty.

[0024] In conjunction with the first aspect, in one possible implementation of the first aspect, the metering accuracy offset value of the smart energy meter is calculated based on the cumulative degradation value corresponding to each key component of the first type, including:

[0025] The cumulative degradation value corresponding to each type of key component is input into the pre-trained metering accuracy offset prediction model to obtain the metering accuracy offset value of the smart energy meter.

[0026] In conjunction with the first aspect, in one possible implementation of the first aspect, predicting whether a smart energy meter is faulty based on the metering accuracy offset value includes:

[0027] Determine whether the measurement accuracy offset value is greater than the preset measurement accuracy offset threshold;

[0028] If the value is greater than the value, it is predicted that the smart energy meter has a metering accuracy failure.

[0029] In conjunction with the first aspect, in one possible implementation of the first aspect, the first type of key components includes a sampling resistor, a voltage divider resistor, and a metering chip; multiple key components also include a power transformer and a clock battery.

[0030] In conjunction with the first aspect, in one possible implementation of the first aspect, the target influencing factors include temperature and humidity.

[0031] Secondly, embodiments of the present invention provide a smart energy meter fault prediction device, comprising:

[0032] The acquisition module is used to acquire the monitoring value of at least one target influencing factor of the smart energy meter;

[0033] The judgment module is used to determine whether the monitoring values ​​of each target influencing factor exceed the standard, and to record the duration of the exceedance corresponding to each target influencing factor whose monitoring value exceeds the standard;

[0034] The calculation module is used to calculate the cumulative degradation value of multiple key components in the smart energy meter based on the monitoring values ​​of each target influencing factor that exceeds the standard and the duration of the exceedance.

[0035] The prediction module is used to determine whether the cumulative degradation value of each key component has reached the preset threshold of each key component. If there is a key component whose degradation value has reached the preset threshold, it is identified as the target key component and the failure of the target key component is predicted.

[0036] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows:

[0037] This invention, through its embodiments, monitors whether the monitored values ​​of various target influencing factors exceed the limits. Based on the monitored values ​​and durations of the exceeding targets, it calculates the cumulative degradation values ​​corresponding to multiple key components in the smart meter to determine whether each key component has failed. On one hand, this invention considers the different impacts of various target influencing factors on different key components, improving the accuracy of fault prediction in smart meters by performing fault assessment on each key component separately. On the other hand, this invention can accurately locate faulty components, improving maintenance efficiency. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a flowchart illustrating the fault prediction method for smart energy meters provided in an embodiment of the present invention.

[0040] Figure 2 This is a schematic diagram of the structure of the smart energy meter provided in an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of the structure of the smart energy meter fault prediction device provided in an embodiment of the present invention. Detailed Implementation

[0042] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0043] Currently, there is a lack of reliability evaluation methods for smart meters based on performance degradation. Most existing methods for evaluating the reliability lifespan of smart meters are based on component datasheets and field failure data. However, the data in these datasheets is outdated and cannot accurately assess the reliability of smart meters. Although some researchers have conducted accelerated degradation tests on the entire smart meter to monitor the degradation of its metering accuracy and thus assess its reliability, this method only considers the overall degradation of the metering accuracy and cannot predict faulty components. Furthermore, it does not consider the impact of other parameter degradation on the reliability of smart meters, such as battery capacity degradation.

[0044] In view of this, see Figure 1 As shown, an embodiment of the present invention provides a method for predicting faults in smart energy meters, comprising:

[0045] Step S101: Obtain the monitoring value of at least one target influencing factor of the smart energy meter.

[0046] The factors affecting the reliability of smart meters are complex and multifaceted, including temperature, humidity, salt spray, low air pressure, electrical stress, and mechanical stress. Therefore, it is first necessary to identify the main factors affecting the reliability of smart meters as target influencing factors.

[0047] Accelerated life testing of smart meters revealed that temperature can cause physical damage, parameter drift, or electrical performance degradation in many electronic components. It can also alter the properties and geometry of electronic materials, thus having the greatest impact on the reliability of chips and electronic components. Humidity can create electrical leakage paths in electronic components, printed circuit boards, and connectors, reducing dielectric strength and insulation, leading to short circuits and open circuits. Increases or decreases in electrical stress directly affect the inherent reliability of electronic components; for heat-generating electronic components such as integrated circuits, resistors, capacitors, and transformers, the impact of electrical stress must be considered. Therefore, the main stresses affecting various functional units can be attributed to temperature, humidity, and electrical stress. However, since the voltage of the power grid system is generally very stable, electrical stress is not considered a primary factor.

[0048] Step S102: Determine whether the monitoring values ​​of each target influencing factor exceed the standard, and record the duration of the exceedance corresponding to each target influencing factor whose monitoring values ​​exceed the standard.

[0049] According to the general technical specifications for smart meters, the extreme operating range of smart meters is -40℃ to 70℃ in temperature and a maximum humidity of 75%RH. To improve the accuracy of the reliable lifespan evaluation of smart meters, this embodiment uses a standard temperature value of 65℃ and a standard humidity value of 65%RH. When the temperature exceeds 65℃, it is considered a temperature violation. When the humidity exceeds 65%RH, it is considered a humidity violation. The duration of temperature and humidity violations is calculated independently and does not affect each other.

[0050] Step S103: Based on the monitoring values ​​and duration of each influencing factor that exceeds the standard, calculate the cumulative degradation value corresponding to multiple key components in the smart energy meter.

[0051] Figure 2This is a schematic diagram of the structure of a smart energy meter provided in this embodiment. Structurally, it can be roughly divided into a metering module, a control module, a power supply module, a clock module, a communication module, and a display module. Common faults in smart energy meters include: display screen damage, metering failure, communication failure, power supply failure, and clock malfunction. According to fault repair data during the lifespan of smart energy meters, the metering module, power supply module, and clock module have the highest failure rates, accounting for over 76% of all smart energy meter failures. Among these, metering unit failures account for more than half of all repair failures, making their impact significant. Therefore, this embodiment primarily monitors the faults of these modules.

[0052] Further analysis of the fault conditions of various components in the metering module revealed that the degradation of the voltage divider resistor, sampling resistor, and metering chip has a significant impact on the output of the smart energy meter metering unit. Therefore, the key components of the metering unit were identified as the voltage divider resistor, sampling resistor, and metering chip.

[0053] It was found that reduced transformer efficiency in the power module leads to increased heat generation, which increases the probability of thermistor malfunction. This causes the smart meter to enter a low-power state when the mains power is normal, making it unable to measure user electricity consumption. Furthermore, the significant heat generated after transformer degradation accelerates the degradation of other components within the meter. Therefore, the power transformer was identified as the key component of the power module.

[0054] Among the causes of clock malfunctions, reduced battery capacity accounted for a significant proportion. When battery capacity degrades, the smart meter's clock will malfunction, causing a large discrepancy between the meter's internal time and the standard time. In addition, battery failure can also lead to issues such as a black LCD screen, CPU failure, and data errors. Therefore, the clock battery was identified as the key component of the clock module.

[0055] That is, in this embodiment, the key components of the smart energy meter include voltage divider resistors, sampling resistors, metering chips, power transformers, and clock batteries.

[0056] Because the effects of the same temperature and humidity on various key components differ (for example, the battery of a smart energy meter has good sealing properties, so humidity has little impact on the internal chemical reaction process and therefore does not affect the battery capacity; the battery is more affected by temperature), this implementation calculates the degradation of each key component separately, which can accurately predict and locate faulty components.

[0057] Step S104: Determine whether the cumulative degradation value of each key component has reached the preset threshold of each key component. If there is a key component whose degradation value has reached the preset threshold, then identify it as the target key component and predict that the target key component will fail.

[0058] In this embodiment, each critical component has a preset threshold for degradation value. When the degradation value of a critical component accumulates to reach the threshold, it indicates that the critical component may have failed.

[0059] As can be seen, this invention, through monitoring whether the monitored values ​​of various target influencing factors exceed the limits, and calculating the cumulative degradation values ​​corresponding to multiple key components in the smart meter based on the monitored values ​​and duration of the exceeding limits, determines whether each key component has failed. On one hand, this invention considers the different impacts of various target influencing factors on different key components, improving the accuracy of fault prediction in smart meters by separately judging the faults of each key component. On the other hand, this invention can accurately locate faulty components, improving maintenance efficiency.

[0060] In one possible implementation, in step S103 above, based on the monitoring values ​​and duration of each influencing factor exceeding the standard, the cumulative degradation values ​​corresponding to multiple key components in the smart energy meter are calculated, including:

[0061] For each key component, based on the monitoring values ​​of each target influencing factor that exceeds the standard, the corresponding degradation factor for each target influencing factor that exceeds the standard is determined;

[0062] The degradation value of the key component in this instance is obtained by summing the products of the degradation factor corresponding to each of the influencing factors that exceed the standard and the duration of the exceedance.

[0063] Based on the current degradation value, determine the cumulative degradation value of the critical component.

[0064] Furthermore, each key component has a pre-set relationship curve between various target influencing factors and degradation factors; for each key component, based on the monitoring values ​​of the exceeding target influencing factors, the corresponding degradation factors for each exceeding target influencing factor are determined, including:

[0065] For each key component, based on the monitoring values ​​and relationship curves of each target influencing factor that exceeds the standard, the degradation factor corresponding to each target influencing factor that exceeds the standard is determined.

[0066] In this embodiment, for example, for a battery, pre-set curves showing the relationship between temperature and degradation factor, and the relationship between humidity and degradation factor. Based on these two curves, the degradation factors corresponding to temperature and humidity can be calculated respectively.

[0067] The product of the degradation factor corresponding to temperature and the duration of exceeding the limit represents the effect of temperature on battery life. Similarly, the product of the degradation factor corresponding to humidity and the duration of exceeding the limit represents the effect of humidity on battery life. Summing these two values ​​yields the battery's degradation value for that specific temperature and humidity level. Accumulating the degradation values ​​obtained for each instance of exceeding the limit gives the battery's cumulative degradation value.

[0068] The relationship curve between the target influencing factors and the degradation factors was determined in the following way:

[0069] For each critical component, the time it takes for the critical component to degrade to failure under multiple different set values ​​of any target influencing factor is obtained, and the degradation factor corresponding to multiple different set values ​​is determined based on the time; wherein, the degradation factor is inversely proportional to time;

[0070] By fitting the degradation factor corresponding to multiple different set values ​​of the target influencing factor, the relationship curve between the target influencing factor and the degradation factor corresponding to the key component is obtained.

[0071] In this embodiment, for example, through a lifespan experiment, the lifespan of each key component is observed at temperatures of 65℃, 70℃, 75℃, 80℃, 85℃, and 95℃. The reciprocal of the lifespan is the degradation factor. For example, at 95℃, if the reference voltage of the metering chip changes from 1.244V to 0.02V on day 30, indicating a fault in the metering reference voltage and complete malfunction of the metering chip, then the degradation factor corresponding to 95℃ is 1 / 30 (it should be noted that this degradation factor is an average value; in reality, the degradation process of each key component is generally relatively stable in the early and middle stages, followed by a sudden and significant degradation in the later stages). The degradation factors at each temperature are fitted to obtain the relationship curve between temperature and degradation factor.

[0072] Substituting the currently monitored temperature into the temperature-degradation factor curve yields the corresponding degradation factor for that temperature. Multiplying the degradation factor by the duration of exceeding the limit gives the degradation value for that temperature. The degradation values ​​corresponding to temperature and humidity are then summed to obtain the current degradation value. It's understandable that if the total usage time of the component is not considered, a degradation value greater than the threshold of 1 indicates component failure. If the total usage time is considered, the threshold should be appropriately reduced; that is, the total usage time of the component is negatively correlated with the threshold.

[0073] As one possible implementation, several key components include a first type of key component, which is a key component that affects the metering accuracy of the smart energy meter.

[0074] The method also includes:

[0075] If the cumulative degradation value corresponding to each type of key component does not reach the preset threshold corresponding to each type of key component, then the metering accuracy offset value of the smart energy meter is calculated based on the cumulative degradation value corresponding to each type of key component.

[0076] Based on the metering accuracy offset value, predict whether the smart energy meter is faulty.

[0077] In this embodiment, to ensure the metering accuracy of the smart energy meter, considering that even if the cumulative degradation values ​​of the key components affecting the metering accuracy have not reached the corresponding preset thresholds, the cumulative impact of each key component on the metering accuracy may still significantly affect the metering accuracy (generally, the degradation process of each key component is relatively stable in the early and middle stages, and then suddenly degrades drastically in the later stages; therefore, it is sufficient to test each key component separately. However, there are also cases where the key components interact, causing a large deviation in the metering accuracy of the smart energy meter). Therefore, this embodiment calculates the metering accuracy deviation value of the smart energy meter based on the cumulative degradation values ​​corresponding to each of the first type of key components, and predicts whether the smart energy meter is faulty.

[0078] Among them, the first type of key components mainly consists of sampling resistors, voltage divider resistors, and metering chips.

[0079] Considering the interaction between the degradation levels of various key components and the metering accuracy of smart meters, this embodiment uses a neural network model to predict metering accuracy.

[0080] That is, based on the cumulative degradation value corresponding to each of the first-type key components, the metering accuracy offset value of the smart energy meter is calculated, including:

[0081] The cumulative degradation value corresponding to each type of key component is input into the pre-trained metering accuracy offset prediction model to obtain the metering accuracy offset value of the smart energy meter.

[0082] Therefore, based on the metering accuracy offset value, it is possible to predict whether a smart energy meter is faulty, including:

[0083] Determine whether the measurement accuracy offset value is greater than the preset measurement accuracy offset threshold;

[0084] If the value is greater than the value, it is predicted that the smart energy meter has a metering accuracy failure.

[0085] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0086] Figure 3This is a schematic diagram of the structure of a smart energy meter fault prediction device provided in an embodiment of the present invention. See also: Figure 3 As shown, the smart energy meter fault prediction device 30 includes:

[0087] The acquisition module 31 is used to acquire the monitoring value of at least one target influencing factor of the smart energy meter;

[0088] The judgment module 32 is used to judge whether the monitoring value of each target influencing factor exceeds the standard, and to record the duration of the exceedance of each target influencing factor whose monitoring value exceeds the standard;

[0089] The calculation module 33 is used to calculate the cumulative degradation value of multiple key components in the smart energy meter based on the monitoring value of each target influencing factor that exceeds the standard and the duration of the exceedance.

[0090] The prediction module 34 is used to determine whether the cumulative degradation value of each key component has reached the preset threshold of each key component. If there is a key component whose degradation value has reached the preset threshold, it is identified as the target key component and the failure of the target key component is predicted.

[0091] As one possible implementation, the computing module 33 is used for:

[0092] For each key component, based on the monitoring values ​​of each target influencing factor that exceeds the standard, the corresponding degradation factor for each target influencing factor that exceeds the standard is determined;

[0093] The degradation value of the key component in this instance is obtained by summing the products of the degradation factor corresponding to each of the influencing factors that exceed the standard and the duration of the exceedance.

[0094] Based on the current degradation value, determine the cumulative degradation value of the critical component.

[0095] As one possible implementation method, each key component has a pre-set relationship curve between various target influencing factors and degradation factors;

[0096] Calculation module 33 is specifically used for:

[0097] For each key component, based on the monitoring values ​​and relationship curves of each target influencing factor that exceeds the standard, the degradation factor corresponding to each target influencing factor that exceeds the standard is determined.

[0098] As one possible approach, the relationship curve between the target influencing factors and the degradation factor is determined in the following way:

[0099] For each critical component, the time it takes for the critical component to degrade to failure under multiple different set values ​​of any target influencing factor is obtained, and the degradation factor corresponding to multiple different set values ​​is determined based on the time; wherein, the degradation factor is inversely proportional to time;

[0100] By fitting the degradation factor corresponding to multiple different set values ​​of the target influencing factor, the relationship curve between the target influencing factor and the degradation factor corresponding to the key component is obtained.

[0101] As one possible implementation, several key components include a first type of key component, which is a key component that affects the metering accuracy of the smart energy meter.

[0102] Prediction module 34 is also used for:

[0103] If the cumulative degradation value corresponding to each type of key component does not reach the preset threshold corresponding to each type of key component, then the metering accuracy offset value of the smart energy meter is calculated based on the cumulative degradation value corresponding to each type of key component.

[0104] Based on the metering accuracy offset value, predict whether the smart energy meter is faulty.

[0105] As one possible implementation, prediction module 34 is specifically used for:

[0106] The cumulative degradation value corresponding to each type of key component is input into the pre-trained metering accuracy offset prediction model to obtain the metering accuracy offset value of the smart energy meter.

[0107] As one possible implementation, prediction module 34 is specifically used for:

[0108] Determine whether the measurement accuracy offset value is greater than the preset measurement accuracy offset threshold;

[0109] If the value is greater than the value, it is predicted that the smart energy meter has a metering accuracy failure.

[0110] As one possible implementation, the first type of key components includes sampling resistors, voltage divider resistors, and metering chips; several other key components also include power transformers and clock batteries.

[0111] As one possible approach, the target influencing factors include temperature and humidity.

[0112] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0113] Those skilled in the art will recognize that the templates, units, and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0114] If a module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various smart energy meter fault prediction method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory, random access memory, electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0115] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for predicting faults in smart energy meters, characterized in that, include: Acquire monitoring values ​​of at least one target influencing factor of the smart energy meter; Determine whether the monitoring values ​​of each target influencing factor exceed the standard, and record the duration of the exceedance corresponding to each target influencing factor whose monitoring value exceeds the standard; Based on the monitoring values ​​and duration of each influencing factor that exceeds the standard, the cumulative degradation values ​​corresponding to multiple key components in the smart energy meter are calculated. Determine whether the cumulative degradation value of each key component reaches the preset threshold corresponding to each key component. If there is a key component whose degradation value reaches the corresponding preset threshold, then identify it as the target key component and predict that the target key component will fail. Each key component has a pre-defined relationship curve between various target influencing factors and degradation factors. These relationship curves are determined in the following way: For each critical component, the time it takes for the critical component to degrade to failure under multiple different set values ​​of any target influencing factor is obtained, and a degradation factor corresponding to multiple different set values ​​is determined based on the time; wherein, the degradation factor is inversely proportional to the time; By fitting the degradation factor corresponding to multiple different set values ​​of the target influencing factor, the relationship curve between the target influencing factor and the degradation factor corresponding to the key component is obtained; The calculation of the cumulative degradation values ​​of multiple key components in the smart energy meter based on the monitoring values ​​and duration of each influencing factor exceeding the standard includes: For each key component, based on the monitoring values ​​of each target influencing factor that exceeds the standard and the respective relationship curves, the degradation factor corresponding to each target influencing factor that exceeds the standard is determined. The degradation value of the key component in this instance is obtained by summing the products of the degradation factor corresponding to each of the influencing factors that exceed the standard and the duration of the exceedance. The cumulative degradation value of the critical component is obtained by summing the degradation values ​​obtained each time the critical component exceeds the standard.

2. The fault prediction method for smart energy meters according to claim 1, characterized in that, The plurality of key components include a first type of key components, which are key components that affect the metering accuracy of the smart energy meter. The method further includes: If the cumulative degradation value corresponding to each of the first type of key components does not reach the preset threshold corresponding to each of the first type of key components, then the metering accuracy offset value of the smart energy meter is calculated based on the cumulative degradation value corresponding to each of the first type of key components. Based on the metering accuracy offset value, it is predicted whether the smart energy meter is faulty.

3. The fault prediction method for smart energy meters according to claim 2, characterized in that, The step of calculating the metering accuracy offset value of the smart energy meter based on the cumulative degradation value corresponding to each of the first type of key components includes: The cumulative degradation value corresponding to each of the first type of key components is input into the pre-trained metering accuracy offset prediction model to obtain the metering accuracy offset value of the smart energy meter.

4. The fault prediction method for smart energy meters according to claim 3, characterized in that, The step of predicting whether the smart meter is faulty based on the metering accuracy offset value includes: Determine whether the measurement accuracy offset value is greater than a preset measurement accuracy offset threshold; If the value is greater than the value, it is predicted that the smart energy meter has a metering accuracy failure.

5. The fault prediction method for smart energy meters according to claim 3, characterized in that, The first type of key components includes sampling resistors, voltage divider resistors, and metering chips; the multiple key components also include power transformers and clock batteries.

6. The fault prediction method for smart energy meters according to claim 1, characterized in that, The target influencing factors include temperature and humidity.

7. A fault prediction device for smart energy meters, characterized in that, Used to implement the smart energy meter fault prediction method as described in any one of claims 1 to 6; The device includes: The acquisition module is used to acquire the monitoring value of at least one target influencing factor of the smart energy meter; The judgment module is used to determine whether the monitoring values ​​of each target influencing factor exceed the standard, and to record the duration of the exceedance corresponding to each target influencing factor whose monitoring value exceeds the standard; The calculation module is used to calculate the cumulative degradation value of multiple key components in the smart energy meter based on the monitoring values ​​of each target influencing factor that exceeds the standard and the duration of the exceedance. The prediction module is used to determine whether the cumulative degradation value of each key component has reached the preset threshold of each key component. If there is a key component whose degradation value has reached the preset threshold, it is identified as the target key component, and the failure of the target key component is predicted.

Images